11 May, 2020

h2.title { font-size: 8px; #color: #a9a9a9; text-align: center; }

Introduction

Dataset:

  • breast cancer

  • proteomics by mass spectrometry

Goal:

  • Explore the dataset for patterns

  • Create models to identify the breast cancer subclasses

Materials and Methods:

Dataset:

Materials and Methods:

  • Exploratory analysis

  • PCA

  • K-means

  • ANN

Materials and Methods:

Materials and Methods:

No definitive effects between expression landscapes and specific tumor subclasses

Breast cancer subtypes in the dataset are well represented

Breast cancer subtypes do not discriminate on age

Breast cancer and gender

Heatmap

Dimentionality reduction

K-means clustering

ANN model’s structure

ANN performance

File structure and reproducibility

Discussion

  • What could have been better

  • further work

The end